BianQue icon indicating copy to clipboard operation
BianQue copied to clipboard

在Python当中调用BianQue-2.0模型时的问题

Open MarcGasol opened this issue 1 year ago • 1 comments

Thanks for your amazing work! 我在python中调用模型时遇到以下问题:

Downloading (…)lve/main/config.json: 100%|██████████████████████████████████████████████| 876/876 [00:00<00:00, 122kB/s]
Explicitly passing a `revision` is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Downloading (…)iguration_chatglm.py: 100%|██████████████████████████████████████████| 4.28k/4.28k [00:00<00:00, 721kB/s]
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Downloading (…)/modeling_chatglm.py: 100%|██████████████████████████████████████████| 57.6k/57.6k [00:00<00:00, 535kB/s]
Downloading (…)main/quantization.py: 100%|█████████████████████████████████████████| 15.1k/15.1k [00:00<00:00, 8.90MB/s]
Downloading (…)model.bin.index.json: 100%|█████████████████████████████████████████| 33.4k/33.4k [00:00<00:00, 4.91MB/s]
Downloading (…)l-00001-of-00003.bin: 100%|█████████████████████████████████████████| 4.96G/4.96G [02:00<00:00, 41.2MB/s]
Downloading (…)l-00002-of-00003.bin: 100%|██████████████████████████████████████████| 4.97G/4.97G [00:22<00:00, 222MB/s]
Downloading (…)l-00003-of-00003.bin: 100%|█████████████████████████████████████████| 3.49G/3.49G [01:27<00:00, 39.6MB/s]
Downloading shards: 100%|█████████████████████████████████████████████████████████████████| 3/3 [03:53<00:00, 77.70s/it]
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████| 3/3 [00:10<00:00,  3.45s/it]
Downloading (…)neration_config.json: 100%|█████████████████████████████████████████████| 147/147 [00:00<00:00, 23.4kB/s]
Downloading (…)okenizer_config.json: 100%|█████████████████████████████████████████████| 522/522 [00:00<00:00, 85.0kB/s]
Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Downloading (…)enization_chatglm.py: 100%|█████████████████████████████████████████| 16.7k/16.7k [00:00<00:00, 6.77MB/s]
Downloading ice_text.model: 100%|██████████████████████████████████████████████████| 2.71M/2.71M [00:00<00:00, 4.54MB/s]
Downloading (…)cial_tokens_map.json: 100%|█████████████████████████████████████████████| 125/125 [00:00<00:00, 66.3kB/s]
The dtype of attention mask (torch.int64) is not bool

请问如何解决这一部分

The dtype of attention mask (torch.int64) is not bool

MarcGasol avatar Jul 07 '23 10:07 MarcGasol

这个警告不影响推理和微调

scutcyr avatar Jul 07 '23 14:07 scutcyr